{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DMW2B7ZGST24DGXEZJVZ75QXGA","short_pith_number":"pith:DMW2B7ZG","schema_version":"1.0","canonical_sha256":"1b2da0ff2694f5c19ae4ca6b9ff617303a1beb208ab88299bbd7a6b726c3d161","source":{"kind":"arxiv","id":"2106.03193","version":1},"attestation_state":"computed","paper":{"title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Angela Fan, Cynthia Gao, Da Ju, Francisco Guzman, Guillaume Wenzek, Marc'Aurelio Ranzato, Naman Goyal, Peng-Jen Chen, Sanjana Krishnan, Vishrav Chaudhary","submitted_at":"2021-06-06T17:58:12Z","abstract_excerpt":"One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES-101 evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional trans"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.03193","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-06T17:58:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86a9e05c412b0cf181c0e7a51ec44d7dcff9a3fbb11f4225f93c070792cc4dbf","abstract_canon_sha256":"1c434fa6d51b2a7954981aec33d6a3c0fc0a821fc3b5b058a8d895b8bdbb1ed7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:47.194181Z","signature_b64":"OVBqAsunT3LvadF8nAXir53wziPoTQIDmVqHMmaFha3Rz7nmdblT8AhPhwD7eTt+i+Mggr6ZPvXZ1OFqYliEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b2da0ff2694f5c19ae4ca6b9ff617303a1beb208ab88299bbd7a6b726c3d161","last_reissued_at":"2026-07-05T02:46:47.193767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:47.193767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Angela Fan, Cynthia Gao, Da Ju, Francisco Guzman, Guillaume Wenzek, Marc'Aurelio Ranzato, Naman Goyal, Peng-Jen Chen, Sanjana Krishnan, Vishrav Chaudhary","submitted_at":"2021-06-06T17:58:12Z","abstract_excerpt":"One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES-101 evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03193","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.03193/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.03193","created_at":"2026-07-05T02:46:47.193823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03193v1","created_at":"2026-07-05T02:46:47.193823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03193","created_at":"2026-07-05T02:46:47.193823+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMW2B7ZGST24","created_at":"2026-07-05T02:46:47.193823+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMW2B7ZGST24DGXE","created_at":"2026-07-05T02:46:47.193823+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMW2B7ZG","created_at":"2026-07-05T02:46:47.193823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20720","citing_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA","json":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA.json","graph_json":"https://pith.science/api/pith-number/DMW2B7ZGST24DGXEZJVZ75QXGA/graph.json","events_json":"https://pith.science/api/pith-number/DMW2B7ZGST24DGXEZJVZ75QXGA/events.json","paper":"https://pith.science/paper/DMW2B7ZG"},"agent_actions":{"view_html":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA","download_json":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA.json","view_paper":"https://pith.science/paper/DMW2B7ZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03193&json=true","fetch_graph":"https://pith.science/api/pith-number/DMW2B7ZGST24DGXEZJVZ75QXGA/graph.json","fetch_events":"https://pith.science/api/pith-number/DMW2B7ZGST24DGXEZJVZ75QXGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA/action/storage_attestation","attest_author":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA/action/author_attestation","sign_citation":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA/action/citation_signature","submit_replication":"https://pith.science/pith/DMW2B7ZGST24DGXEZJVZ75QXGA/action/replication_record"}},"created_at":"2026-07-05T02:46:47.193823+00:00","updated_at":"2026-07-05T02:46:47.193823+00:00"}